Related papers: FastVAR: Linear Visual Autoregressive Modeling via…

Vision-Language-Action (VLA) models offer a unified framework for robotic perception and control, but their ability to scale to real-world, long-horizon tasks is limited by the high computational cost of attention and the large memory…

Multi-view 3D reconstruction remains a core challenge in computer vision, particularly in applications requiring accurate and scalable representations across diverse perspectives. Current leading methods such as DUSt3R employ a…

Visual autoregressive (VAR) models have recently emerged as an efficient paradigm for text-to-image generation. Despite their strong generative capability, existing VAR-based personalization methods remain limited to static settings,…

Vision-Language Models (VLMs) have emerged as a promising paradigm in autonomous driving (AD), providing a unified framework for perception and decision-making. However, their real-world deployment is hindered by significant computational…

Vision-language models (VLMs) excel at image understanding tasks, but the large number of visual tokens imposes significant computational costs, hindering deployment on mobile devices. Many pruning methods rely solely on token importance…

Autoregressive Transformers are increasingly being deployed as end-to-end robot and autonomous vehicle (AV) policy architectures, owing to their scalability and potential to leverage internet-scale pretraining for generalization.…

Vision-Language-Navigation (VLN) models exhibit excellent navigation accuracy but incur high computational overhead. Token caching has emerged as a promising training-free strategy to reduce this cost by reusing token computation results;…

In the field of instruction-following large vision-language models (LVLMs), the efficient deployment of these models faces challenges, notably due to the high memory demands of their key-value (KV) caches. Conventional cache management…

Diffusion-based large multimodal models, such as LLaDA-V, have demonstrated impressive capabilities in vision-language understanding and generation. However, their bidirectional attention mechanism and diffusion-style iterative denoising…

We present LightVLA, a simple yet effective differentiable token pruning framework for vision-language-action (VLA) models. While VLA models have shown impressive capability in executing real-world robotic tasks, their deployment on…

We reinterpret Visual Autoregressive (VAR) models as iterative refinement models to identify which design choices drive their quality-efficiency trade-off. Instead of treating VAR only as next-scale autoregression, we formalise it as a…

Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we address this limitation by exploiting the temporal redundancy inherent in video latent patches. To…

Medical image generation is pivotal in applications like data augmentation for low-resource clinical tasks and privacy-preserving data sharing. However, developing a scalable generative backbone for medical imaging requires architectural…

Despite significant progress in 3D avatar reconstruction, it still faces challenges such as high time complexity, sensitivity to data quality, and low data utilization. We propose FastAvatar, a feedforward 3D avatar framework capable of…

Flow Matching models achieve state-of-the-art image generation quality but incur substantial inference cost due to iterative denoising through large Transformer networks. We observe that different layer groups within a Transformer exhibit…

Recent advancements in Vision-Language Models (VLMs) enable large language models (LLMs) to process high-resolution images, significantly improving real-world multimodal understanding. However, this capability introduces a large number of…

Autoregressive sequence models, such as Transformer-based vision-language action (VLA) policies, can be tremendously effective for capturing complex and generalizable robotic behaviors. However, such models require us to choose a…

Although current Video-LLMs achieve impressive performance in video understanding tasks, their autoregressive decoding efficiency remains constrained by the massive number of video tokens. Visual token pruning can partially ease this…

We investigate methods to reduce inference time and memory footprint in stable diffusion models by introducing lightweight decoders for both image and video synthesis. Traditional latent diffusion pipelines rely on large Variational…

Visual token pruning is a promising approach for reducing the computational cost of vision-language models (VLMs), and existing methods often rely on early pruning decisions to improve efficiency. While effective on coarse-grained reasoning…